Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 400 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2683. Min Act: -0.0001

Data Index: 433763 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2542. Min Act: -0.0001

Data Index: 899236 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2535. Min Act: -0.0001

Data Index: 758922 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2502. Min Act: -0.0000

Data Index: 1006379 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2442. Min Act: -0.0000

Data Index: 1411490 (Python Code)

Max Activating Token Index: 784

Text #5

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2406. Min Act: -0.0000

Data Index: 1574497 (Python Code)

Max Activating Token Index: 523

Text #6

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2326. Min Act: -0.0000

Data Index: 45591 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2257. Min Act: -0.0001

Data Index: 438236 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2141. Min Act: -0.0000

Data Index: 651832 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2129. Min Act: -0.0001

Data Index: 502568 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2114. Min Act: -0.0001

Data Index: 19330 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2081. Min Act: -0.0000

Data Index: 486326 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2115. Min Act: -0.0000

Data Index: 332203 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2110. Min Act: -0.0001

Data Index: 369194 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2103. Min Act: -0.0001

Data Index: 982590 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2111. Min Act: -0.0000

Data Index: 707155 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2054. Min Act: -0.0001

Data Index: 6163 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2157. Min Act: -0.0001

Data Index: 175119 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2067. Min Act: -0.0001

Data Index: 751854 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2067. Min Act: -0.0001

Data Index: 662341 (C4 (Web Text))

Max Activating Token Index: 65